Search Results for author:
Found 21 papers, 1 papers with code
Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems
However the traditional RBM architecture and the commonly used training algorithm known as Contrastive Divergence (CD) are based on discrete updates and exact arithmetics which do not directly map onto a dynamical neural substrate.
Learning Non-deterministic Representations with Energy-based Ensembles
These mappings are encoded in a distribution over a (possibly infinite) collection of models.
Gibbs Sampling with Low-Power Spiking Digital Neurons
Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in a wide variety of applications including image classification and speech recognition.
Mapping Generative Models onto a Network of Digital Spiking Neurons
For this, we first propose a method of producing the Gibbs sampler using bio-inspired digital noisy integrate-and-fire neurons.
Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex.
Forward Table-Based Presynaptic Event-Triggered Spike-Timing-Dependent Plasticity
We present a novel method for realizing both causal and acausal weight updates using only forward lookup access of the synaptic connectivity table, permitting memory-efficient implementation.
Training a Probabilistic Graphical Model with Resistive Switching Electronic Synapses
Current large scale implementations of deep learning and data mining require thousands of processors, massive amounts of off-chip memory, and consume gigajoules of energy.
Membrane-Dependent Neuromorphic Learning Rule for Unsupervised Spike Pattern Detection
Several learning rules for synaptic plasticity, that depend on either spike timing or internal state variables, have been proposed in the past imparting varying computational capabilities to Spiking Neural Networks.
Hardware-efficient on-line learning through pipelined truncated-error backpropagation in binary-state networks
In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation.
A learning framework for winner-take-all networks with stochastic synapses
This allows us to use the proposed networks in a variational learning setting where stochastic backpropagation is used to optimize a lower bound on the data log likelihood, thereby learning a generative model of the data.
Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning
Embedded, continual learning for autonomous and adaptive behavior is a key application of neuromorphic hardware.
Deep supervised learning using local errors
Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from higher layers.
Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the brain
Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.
Edge AI without Compromise: Efficient, Versatile and Accurate Neurocomputing in Resistive Random-Access Memory
Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e. g. video, audio) at unprecedented energy-efficiency.
NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems
The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings.
Active Inference in Hebbian Learning Networks
This work studies how brain-inspired neural ensembles equipped with local Hebbian plasticity can perform active inference (AIF) in order to control dynamical agents.
An Exploration of Optimal Parameters for Efficient Blind Source Separation of EEG Recordings Using AMICA
A multitude of ICA algorithms for EEG decomposition exist, and in the past, their relative effectiveness has been studied.
Integrating LLM, EEG, and Eye-Tracking Biomarker Analysis for Word-Level Neural State Classification in Semantic Inference Reading Comprehension
With the recent proliferation of large language models (LLMs), such as Generative Pre-trained Transformers (GPT), there has been a significant shift in exploring human and machine comprehension of semantic language meaning.
Multi-level, Forming Free, Bulk Switching Trilayer RRAM for Neuromorphic Computing at the Edge
To address all these challenges, we developed a forming-free and bulk switching RRAM technology based on a trilayer metal-oxide stack.
Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling
Our results show that the proposed approach strongly outperforms the use of backprop by up to $27\%$ higher accuracy when subject to strong hardware non-idealities.
Energy-efficiency Limits on Training AI Systems using Learning-in-Memory
In this paper, we derive new theoretical lower bounds on energy dissipation when training AI systems using different LIM approaches.
